DeepKeep Ltd.

BS"D

DeepKeep, a startup among the past year's winners of the EIC Accelerator, develops security and trustworthiness solutions for AI systems.

Primarily addressing LLMs, agentic systems and image processing systems we aim to provide:

1. Algorithmic risk assessment of AI systems (e.g. is the model vulnerable to evasion/jailbreak attacks that force it provide illegal/harmful information? are there any trustworthiness issues ? is the model unfair? does the LLM leak sensitive private data? etc.)

2. AI firewall solution (e.g. additional real-time layer that enhances algorithmic security and trustworthiness) including detection and mitigation of evasion/jailbreak attacks, handling data leakage etc.

3. Technologies that help in AI regulation compliance evaluation/enhancement.

Key advantages of DeepKeep include:

• Native multi-lingual support.

• Context aware customization of red teaming and firewall features

• Option for On-Prem/Private-cloud deployment of DeepKeep's platform allowing for local (privacy preserving) processing of sensitive data.

• Company has capabilities in multiple modailities/AI types: Vision, LLM Agentic systems

These solutions handle multiple issues including:

1. AI systems performance Evaluation

2. Sensitive data leakage prevention

3. Hallucination handling

4. LLM guardrails (securing alignment of the LLM to certain topics),

5. Prevention of malicious jailbreak/prompt injection attacks.

6. Image data augmentation using GenAI

7. Vision systems’ failure modes analysis and weak spot detection

8. Evasion attacks on vision systems

9. Fairness and Bias issues And more